| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 11110, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0450070323488045, |
| "grad_norm": 1.15119469165802, |
| "learning_rate": 4.7754275427542756e-05, |
| "loss": 0.7194, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.090014064697609, |
| "grad_norm": 0.7163170576095581, |
| "learning_rate": 4.55040504050405e-05, |
| "loss": 0.5608, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.1350210970464135, |
| "grad_norm": 0.7999687194824219, |
| "learning_rate": 4.325382538253826e-05, |
| "loss": 0.5131, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.180028129395218, |
| "grad_norm": 0.7465606927871704, |
| "learning_rate": 4.1003600360036004e-05, |
| "loss": 0.4862, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.2250351617440225, |
| "grad_norm": 0.6740167140960693, |
| "learning_rate": 3.875337533753375e-05, |
| "loss": 0.4732, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.270042194092827, |
| "grad_norm": 0.6270012855529785, |
| "learning_rate": 3.6503150315031505e-05, |
| "loss": 0.4551, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.3150492264416315, |
| "grad_norm": 0.6703944802284241, |
| "learning_rate": 3.425292529252925e-05, |
| "loss": 0.4389, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.360056258790436, |
| "grad_norm": 0.5351672768592834, |
| "learning_rate": 3.2002700270027e-05, |
| "loss": 0.4301, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.4050632911392405, |
| "grad_norm": 0.5910940170288086, |
| "learning_rate": 2.9752475247524754e-05, |
| "loss": 0.4211, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.450070323488045, |
| "grad_norm": 0.5866793394088745, |
| "learning_rate": 2.75022502250225e-05, |
| "loss": 0.4167, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.49507735583684953, |
| "grad_norm": 0.5274554491043091, |
| "learning_rate": 2.525202520252025e-05, |
| "loss": 0.4063, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.540084388185654, |
| "grad_norm": 0.5235472917556763, |
| "learning_rate": 2.3001800180018002e-05, |
| "loss": 0.4013, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.5850914205344585, |
| "grad_norm": 0.5259997844696045, |
| "learning_rate": 2.0751575157515752e-05, |
| "loss": 0.3956, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.630098452883263, |
| "grad_norm": 0.5384368300437927, |
| "learning_rate": 1.85013501350135e-05, |
| "loss": 0.393, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.6751054852320675, |
| "grad_norm": 0.6394015550613403, |
| "learning_rate": 1.625112511251125e-05, |
| "loss": 0.3891, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.720112517580872, |
| "grad_norm": 0.6722325682640076, |
| "learning_rate": 1.4000900090009e-05, |
| "loss": 0.3857, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.7651195499296765, |
| "grad_norm": 0.6460537910461426, |
| "learning_rate": 1.1750675067506751e-05, |
| "loss": 0.3828, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.810126582278481, |
| "grad_norm": 0.6135509610176086, |
| "learning_rate": 9.500450045004502e-06, |
| "loss": 0.3764, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.8551336146272855, |
| "grad_norm": 0.5668925046920776, |
| "learning_rate": 7.250225022502251e-06, |
| "loss": 0.3753, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.90014064697609, |
| "grad_norm": 0.5281524062156677, |
| "learning_rate": 5e-06, |
| "loss": 0.3772, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.9451476793248945, |
| "grad_norm": 0.6521788835525513, |
| "learning_rate": 2.7497749774977497e-06, |
| "loss": 0.3767, |
| "step": 10500 |
| }, |
| { |
| "epoch": 0.9901547116736991, |
| "grad_norm": 0.6250452399253845, |
| "learning_rate": 4.995499549954995e-07, |
| "loss": 0.3726, |
| "step": 11000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 11110, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 99999999, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.3994760575488e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
